Greg Hanneman

General Contact:
Language Technologies Institute
Carnegie Mellon University
Gates Hillman Complex 5407
5000 Forbes Avenue
Pittsburgh, PA 15213

Personal Contact:
Mailbox: Gates Hillman Complex 5404
E-mail: ghannema [at] cs [dot] cmu [dot] edu

Current Work

I am a final-year graduate student at the LTI, advised by Alon Lavie. My main research focus is on syntactic models for machine translation — that is, automatically translating human-language text based on knowledge of linguistic divergences between languages. For my thesis project, I'm working on automatic ways of optimizing part-of-speech and constituent labels used in synchronous context-free grammars for MT. See my "Publications" page for a link to the full thesis proposal document.

My other specialty these days seems to be reviewing. I've been on the program committees for WMT 2011, 2012, 2013, and 2014; SSST-7 (2013); and MT Summit 2013. At larger conferences, I've reviewed for the machine translation tracks of NAACL 2013, EMNLP 2012 (where I was named one of the best reviewers) and 2014, and EACL 2012 and 2014.

Since August 2012, I've actually been working (mostly) full-time for Safaba Translation Solutions, a start-up company offering customized MT systems to corporate clients. You can still catch me around the LTI on Thursdays, though, and the Safaba office is just up the road in Squirrel Hill!

I spent the fall 2009 semester on internship at the Xerox Research Centre Europe in Grenoble, France. My project there was on word alignment and phrase extraction methods for statistical machine translation. As a master's student, I originally started my graduate research in multi-engine translation (system combination).


See my full publication list for all citations, paper links, and slides. Recent papers include a portion of my thesis work on collapsing syntactic category labels (at the ACL 2011 SSST workshop) and a further extension of the same algorithm to the Syntax-Augmented MT formalism (at NAACL 2013).


I was one of the Spring 2012 TAs for Formal Languages, Automata, and Computability (15-453). Before that, I was the Fall 2007 TA for Algorithms for Natural Language Processing (11-711).

During the spring of 2011, I designed and taught a student-led course on college journalism, The Process to the Press (98-148). I co-taught the class again in Spring 2012 with Patrick Gage Kelley.


Fall 2011:

11-700: LTI Colloquium

Spring 2012:

11-700: LTI Colloquium

11-734: Advanced MT Seminar

Fall 2010:

11-700: LTI Colloquium

Spring 2011:

11-700: LTI Colloquium

Fall 2009:


Spring 2010:

11-700: LTI Colloquium

11-734: Advanced MT Seminar

98-142: Drawing What You See (StuCo)

Fall 2008:

10-701: Machine Learning

Spring 2009:

62-241: Black and White Photography II

Fall 2007:


Spring 2008:

11-734: Advanced MT Seminar

76-857: Historical Linguistics

Fall 2006:

11-762: Language and Statistics II

11-791: Software Engineering

82-303: French Culture

Spring 2007:

11-731: Machine Translation

11-792: Software Engineering II

Fall 2005:

11-711: Algorithms for Natural Language Processing

11-721: Grammars and Lexicons

Spring 2006:

11-712: Self-Directed NLP Lab

11-722: Grammar Formalisms

11-761: Language and Statistics

Outside Interests

I'm a senior staff member of The Tartan, CMU's student newspaper, where I also previously served on the executive committee, managed the copy department, and wrote articles for the news section. Aside from a certain neurotic obsession with writing and editing that I picked up from my newspaper work, I first got interested in language by studying French in high school and as an undergraduate. I also enjoy picking out speech variations and "accents" from different parts of the U.S. When I'm not thinking about things academic, I try to make time for photography (and developing my own black-and-white prints), reading, camping, running, and playing In the Groove. I've also recently started learning Thai.

My growing digital photography site is here. There are some galleries for photos from "professional" trips: Prague (for the MT Marathon 2009); Boulder, Colo. (for NAACL 2009); Edinburgh (for EMNLP 2011); Atlanta (for NAACL 2013).

My talk on machine "translation" won the Best Presentation Award at SIGBOVIK 2010.

Past Life

In May 2005 I received a B.S. degree in computer science with a minor in French from Case Western Reserve University in Cleveland, Ohio. I spent all eight semesters at Case as a staff member of The Observer student newspaper, where I was a reporter, layout editor, copy editor, and news editor. I'm originally from the Cleveland suburbs.

Page created 26 August 2005; last updated 1 July 2014.